{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T11:56:32Z","timestamp":1776426992755,"version":"3.51.2"},"reference-count":62,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T00:00:00Z","timestamp":1733788800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>In today\u2019s rapidly evolving digital landscape, customer reviews play a crucial role in shaping the reputation and success of hotels. Accurately analyzing and classifying the sentiment of these reviews offers valuable insights into customer satisfaction, enabling businesses to gain a competitive edge. This study undertakes a comparative analysis of traditional natural language processing (NLP) models, such as BERT and advanced large language models (LLMs), specifically GPT-4 omni and GPT-4o mini, both pre- and post-fine-tuning with few-shot learning. By leveraging an extensive dataset of hotel reviews, we evaluate the effectiveness of these models in predicting star ratings based on review content. The findings demonstrate that the GPT-4 omni family significantly outperforms the BERT model, achieving an accuracy of 67%, compared to BERT\u2019s 60.6%. GPT-4o, in particular, excelled in accuracy and contextual understanding, showcasing the superiority of advanced LLMs over traditional NLP methods. This research underscores the potential of using sophisticated review evaluation systems in the hospitality industry and positions GPT-4o as a transformative tool for sentiment analysis. It marks a new era in automating and interpreting customer feedback with unprecedented precision.<\/jats:p>","DOI":"10.3390\/info15120792","type":"journal-article","created":{"date-parts":[[2024,12,10]],"date-time":"2024-12-10T11:17:20Z","timestamp":1733829440000},"page":"792","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["Leveraging Large Language Models in Tourism: A Comparative Study of the Latest GPT Omni Models and BERT NLP for Customer Review Classification and Sentiment Analysis"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8098-1616","authenticated-orcid":false,"given":"Konstantinos I.","family":"Roumeliotis","sequence":"first","affiliation":[{"name":"Department of Digital Systems, University of the Peloponnese, 23100 Sparta, Greece"},{"name":"Department of Informatics and Telecommunications, University of the Peloponnese, 22131 Tripoli, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5799-3558","authenticated-orcid":false,"given":"Nikolaos D.","family":"Tselikas","sequence":"additional","affiliation":[{"name":"Department of Informatics and Telecommunications, University of the Peloponnese, 22131 Tripoli, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7386-1029","authenticated-orcid":false,"given":"Dimitrios K.","family":"Nasiopoulos","sequence":"additional","affiliation":[{"name":"Department of Agribusiness and Supply Chain Management, School of Applied Economics and Social Sciences, Agricultural University of Athens, 11855 Athens, Greece"}]}],"member":"1968","published-online":{"date-parts":[[2024,12,10]]},"reference":[{"key":"ref_1","unstructured":"(2024, October 11). Travel and Tourism: Contribution to Global GDP 2023 | Statista. Available online: https:\/\/www.statista.com\/statistics\/233223\/travel-and-tourism-total-economic-contribution-worldwide\/."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1177\/00222429231191449","article-title":"The Competitive Effects of Online Reviews on Hotel Demand","volume":"88","author":"Cho","year":"2023","journal-title":"J. Mark."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Zheng, W., and Ye, Q. (2009, January 21\u201322). Sentiment Classification of Chinese Traveler Reviews by Support Vector Machine Algorithm. Proceedings of the 3rd International Symposium on Intelligent Information Technology Application, IITA 2009, Nanchang, China.","DOI":"10.1109\/IITA.2009.457"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Borrajo-Mill\u00e1n, F., Alonso-Almeida, M.d.M., Escat-cortes, M., and Yi, L. (2021). Sentiment Analysis to Measure Quality and Build Sustainability in Tourism Destinations. Sustainability, 13.","DOI":"10.3390\/su13116015"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Wadhe, A.A., and Suratkar, S.S. (2020, January 13\u201315). Tourist Place Reviews Sentiment Classification Using Machine Learning Techniques. Proceedings of the 2020 International Conference on Industry 4.0 Technology, I4Tech 2020, Pune, India.","DOI":"10.1109\/I4Tech48345.2020.9102673"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"122493","DOI":"10.1016\/j.eswa.2023.122493","article-title":"Aspect-Based Sentiment Score and Star Rating Prediction for Travel Destination Using Multinomial Logistic Regression with Fuzzy Domain Ontology Algorithm","volume":"240","author":"Kumar","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"7408431","DOI":"10.1155\/2018\/9327536","article-title":"Using Deep Learning to Predict Sentiments: Case Study in Tourism","volume":"2018","author":"Torres","year":"2018","journal-title":"Complexity"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Li, Q., Li, S., Hu, J., Zhang, S., and Hu, J. (2018). Tourism Review Sentiment Classification Using a Bidirectional Recurrent Neural Network with an Attention Mechanism and Topic-Enriched Word Vectors. Sustainability, 10.","DOI":"10.3390\/su10093313"},{"key":"ref_9","first-page":"100658","article-title":"Sentiment Analyses of Multilingual Tweets on Halal Tourism","volume":"34","author":"Ainin","year":"2020","journal-title":"Tour. Manag. Perspect."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Qi, J., Yan, S., Zhang, W., Zhang, Y., Liu, Z., and Wang, K. (2024, January 21\u201323). Research on Tibetan Tourism Viewpoints Information Generation System Based on LLM. Proceedings of the 2024 12th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC), Chongqing, China.","DOI":"10.1109\/ICWOC62055.2024.10684948"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100056","DOI":"10.1016\/j.nlp.2024.100056","article-title":"LLMs in E-Commerce: A Comparative Analysis of GPT and LLaMA Models in Product Review Evaluation","volume":"6","author":"Roumeliotis","year":"2024","journal-title":"Nat. Lang. Process. J."},{"key":"ref_12","unstructured":"(2024, October 11). Models\u2014OpenAI API. Available online: https:\/\/platform.openai.com\/docs\/models."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.3390\/jtaer17040070","article-title":"Multichannel Digital Marketing Optimizations through Big Data Analytics in the Tourism and Hospitality Industry","volume":"17","author":"Sakas","year":"2022","journal-title":"J. Theor. Appl. Electron. Commer. Res."},{"key":"ref_14","first-page":"3563","article-title":"Sentiment Analysis from Unstructured Hotel Reviews Data in Social Network Using Deep Learning Techniques","volume":"15","author":"Priya","year":"2023","journal-title":"Int. J. Inf. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e02753822023-18","DOI":"10.1371\/journal.pone.0275382","article-title":"Sentiment Analysis of Hotel Online Reviews Using the BERT Model and ERNIE Model\u2014Data from China","volume":"18","author":"Wen","year":"2023","journal-title":"PLoS ONE"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e17147","DOI":"10.1016\/j.heliyon.2023.e17147","article-title":"Deep Learning-Based Application for Multilevel Sentiment Analysis of Indonesian Hotel Reviews","volume":"9","author":"Kusumaningrum","year":"2023","journal-title":"Heliyon"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"e12580","DOI":"10.1111\/exsy.12580","article-title":"An Improved Model for Sentiment Analysis on Luxury Hotel Review","volume":"40","author":"Chang","year":"2023","journal-title":"Expert Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"103527","DOI":"10.1016\/j.ipm.2023.103527","article-title":"Leveraging Online Reviews for Hotel Demand Forecasting: A Deep Learning Approach","volume":"61","author":"Zhang","year":"2024","journal-title":"Inf. Process. Manag."},{"key":"ref_19","first-page":"569","article-title":"Customer Sentiment Analysis in Hotel Reviews Through Natural Language Processing Techniques","volume":"14","author":"Ounacer","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"102930","DOI":"10.1016\/j.ijhm.2021.102930","article-title":"A Systematic Review of AI Technology-Based Service Encounters: Implications for Hospitality and Tourism Operations","volume":"95","author":"Li","year":"2021","journal-title":"Int. J. Hosp. Manag."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3199","DOI":"10.1108\/IJCHM-04-2020-0259","article-title":"Adoption of AI-Based Chatbots for Hospitality and Tourism","volume":"32","author":"Pillai","year":"2020","journal-title":"Int. J. Contemp. Hosp. Manag."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.1108\/JHTI-01-2021-0021","article-title":"When Artificial Intelligence Meets the Hospitality and Tourism Industry: An Assessment Framework to Inform Theory and Management","volume":"5","author":"Huang","year":"2022","journal-title":"J. Hosp. Tour. Insights"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"103642","DOI":"10.1016\/j.annals.2023.103642","article-title":"Text-to-Image AI Tools and Tourism Experiences","volume":"102","author":"Miao","year":"2023","journal-title":"Ann. Tour. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/MNET.011.2000250","article-title":"Realizing the Potential of Internet of Things for Smart Tourism with 5G and AI","volume":"34","author":"Wang","year":"2020","journal-title":"IEEE Netw."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1177\/0047287520971054","article-title":"Tourists\u2019 Attitudes toward the Use of Artificially Intelligent (AI) Devices in Tourism Service Delivery: Moderating Role of Service Value Seeking","volume":"61","author":"Chi","year":"2022","journal-title":"J. Travel Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1007\/s10796-022-10271-8","article-title":"The Future Is Yesterday: Use of AI-Driven Facial Recognition to Enhance Value in the Travel and Tourism Industry","volume":"25","author":"Gupta","year":"2023","journal-title":"Inf. Syst. Front."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1887","DOI":"10.1080\/10447318.2022.2124345","article-title":"\u201cI Am Here to Assist Your Tourism\u201d: Predicting Continuance Intention to Use AI-Based Chatbots for Tourism. Does Gender Really Matter?","volume":"39","author":"Zhang","year":"2023","journal-title":"Int. J. Hum. Comput. Interact."},{"key":"ref_28","unstructured":"Wei, Q., Yang, M., Wang, J., Mao, W., Xu, J., and Ning, H. (2024). TourLLM: Enhancing LLMs with Tourism Knowledge. arXiv, Available online: https:\/\/arxiv.org\/abs\/2407.12791v1."},{"key":"ref_29","unstructured":"Banerjee, A., Satish, A., and W\u00f6rndl, W. (2024). Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generation. arXiv, Available online: https:\/\/arxiv.org\/abs\/2409.18003v1."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1007\/978-3-031-71710-9_18","article-title":"LLM-Aided Museum Guide: Personalized Tours Based on User Preferences","volume":"Volume 15029","author":"Vasic","year":"2024","journal-title":"International Conference on Extended Reality"},{"key":"ref_31","unstructured":"Chen, B.O., Chen, B., Dai, X., Guo, H., Guo, W., Liu, W., Liu, Y., Qin, J., Tang, R., and Wang, Y. (2024). All Roads Lead to Rome: Unveiling the Trajectory of Recommender Systems Across the LLM Era. arXiv, Available online: https:\/\/arxiv.org\/abs\/2407.10081v1."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Balamurali, O., Abhishek Sai, A.M., Karthikeya, M., and Anand, S. (2023, January 21\u201323). Sentiment Analysis for Better User Experience in Tourism Chatbot Using LSTM and LLM. Proceedings of the 2023 9th International Conference on Signal Processing and Communication, ICSC 2023, Noida, India.","DOI":"10.1109\/ICSC60394.2023.10441148"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"99755","DOI":"10.1109\/ACCESS.2024.3429290","article-title":"Harnessing the Power of LLMs for Service Quality Assessment from User-Generated Content","volume":"12","author":"Falatouri","year":"2024","journal-title":"IEEE Access"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"45","DOI":"10.18089\/tms.2024SI04","article-title":"Artificial Intelligence and Sustainable Tourism Planning: A Hetero-Intelligence Methodology Proposal","volume":"20","author":"Santos","year":"2024","journal-title":"Tour. Manag. Stud."},{"key":"ref_35","first-page":"343","article-title":"Knowledge Graphs and Large Language Models for Intelligent Applications in the Tourism Domain","volume":"7","author":"Secchi","year":"2024","journal-title":"Universit\u00e0 di Cagliari"},{"key":"ref_36","first-page":"179","article-title":"Rapid development of chatbot for tourism promotion in Latgale","volume":"2","author":"Kodors","year":"2024","journal-title":"Environ. Technol. Resour. Proc. Int. Sci. Pract. Conf."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"103723","DOI":"10.1016\/j.annals.2023.103723","article-title":"A Fine-Tuned Tourism-Specific Generative AI Concept","volume":"104","author":"Hsu","year":"2024","journal-title":"Ann. Tour. Res."},{"key":"ref_38","unstructured":"Qi, J., Yan, S., Zhang, Y., Zhang, W., Jin, R., Hu, Y., and Wang, K. (2024). RAG-Optimized Tibetan Tourism LLMs: Enhancing Accuracy and Personalization. arXiv, Available online: https:\/\/arxiv.org\/abs\/2408.12003v1."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Balfroid, M., Vanderose, B., and Devroey, X. (2024, January 20). Towards LLM-Generated Code Tours for Onboarding. Proceedings of the 2024 ACM\/IEEE International Workshop on NL-Based Software Engineering, NLBSE 2024, Lisbon, Portugal.","DOI":"10.1145\/3643787.3648033"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1108\/EL-06-2023-0160","article-title":"Enhancing Knowledge Graphs with Microdata and LLMs: The Case of Schema.Org and Wikidata in Touristic Information","volume":"42","year":"2024","journal-title":"Electron. Libr."},{"key":"ref_41","unstructured":"Meyer, S., Singh, S., Tam, B., Ton, C., and Ren, A. (2024). A Comparison of LLM Finetuning Methods & Evaluation Metrics with Travel Chatbot Use Case. arXiv, Available online: https:\/\/arxiv.org\/abs\/2408.03562v1."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1108\/TR-02-2023-0088","article-title":"ChatGPT for Tourism: Applications, Benefits and Risks","volume":"79","author":"Carvalho","year":"2024","journal-title":"Tour. Rev."},{"key":"ref_43","first-page":"82","article-title":"Comparative Analysis of Large Language Models in Structured Information Extraction from Job Postings","volume":"2141","author":"Sioziou","year":"2024","journal-title":"Commun. Comput. Inf. Sci."},{"key":"ref_44","unstructured":"Liyanage, V., Buscaldi, D., and Forcioli, P. (2024, October 12). Detecting AI-Enhanced Opinion Spambots: A Study on LLM-Generated Hotel Reviews. Available online: https:\/\/aclanthology.org\/2024.ecnlp-1.8."},{"key":"ref_45","unstructured":"(2024, October 13). Trip Advisor Hotel Reviews. Available online: https:\/\/www.kaggle.com\/datasets\/andrewmvd\/trip-advisor-hotel-reviews#."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"206","DOI":"10.1016\/j.ins.2016.01.013","article-title":"Joint Multi-Grain Topic Sentiment: Modeling Semantic Aspects for Online Reviews","volume":"339","author":"Alam","year":"2016","journal-title":"Inf. Sci."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Roumeliotis, K.I., Tselikas, N.D., Nasiopoulos, D.K., Roumeliotis, K.I., Tselikas, N.D., and Nasiopoulos, D.K. (2024). Next-Generation Spam Filtering: Comparative Fine-Tuning of LLMs, NLPs, and CNN Models for Email Spam Classification. Electronics, 13.","DOI":"10.3390\/electronics13112034"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"102038","DOI":"10.1016\/j.inffus.2023.102038","article-title":"Semantic Understanding and Prompt Engineering for Large-Scale Traffic Data Imputation","volume":"102","author":"Zhang","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_49","unstructured":"(2017). Information Technology\u2014The JSON Data Interchange Syntax (Standard No. ISO\/IEC 21778:2017)."},{"key":"ref_50","unstructured":"(2024, November 27). Fine-Tuning\u2014OpenAI API. Available online: https:\/\/platform.openai.com\/docs\/guides\/fine-tuning."},{"key":"ref_51","first-page":"39682","article-title":"Any-Precision LLM: Low-Cost Deployment of Multiple, Different-Sized LLMs","volume":"235","author":"Park","year":"2024","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1007\/s10772-021-09825-z","article-title":"Efficient Diabetes Mellitus Prediction with Grid Based Random Forest Classifier in Association with Natural Language Processing","volume":"24","author":"Abokhzam","year":"2021","journal-title":"Int. J. Speech Technol."},{"key":"ref_53","first-page":"281","article-title":"Random Search for Hyper-Parameter Optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref_54","unstructured":"Watanabe, S. (2023). Tree-Structured Parzen Estimator: Understanding Its Algorithm Components and Their Roles for Better Empirical Performance. arXiv."},{"key":"ref_55","unstructured":"(2023, December 17). Pretrained Models\u2014Transformers 3.3.0 Documentation. Available online: https:\/\/huggingface.co\/transformers\/v3.3.1\/pretrained_models.html."},{"key":"ref_56","unstructured":"(2024, October 19). GitHub\u2014Applied-AI-Research-Lab\/LLMs-in-Tourism-GPT-4-Omni-vs-BERT: Leveraging LLMs in Tourism: A Comparative Study of the Latest GPT Omni Models and BERT NLP for Customer Review Classification and Sentiment. Available online: https:\/\/github.com\/Applied-AI-Research-Lab\/LLMs-in-Tourism-GPT-4-omni-vs-BERT\/tree\/main."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Roumeliotis, K.I., Tselikas, N.D., and Nasiopoulos, D.K. (2024). LLMs and NLP Models in Cryptocurrency Sentiment Analysis: A Comparative Classification Study. Big Data Cogn. Comput., 8.","DOI":"10.3390\/bdcc8060063"},{"key":"ref_58","unstructured":"(2024, October 16). What Is GPT-4o Mini?. How It Works, Use Cases, API & More | DataCamp., Available online: https:\/\/www.datacamp.com\/blog\/gpt-4o-mini."},{"key":"ref_59","unstructured":"(2024, October 18). Pricing | OpenAI. Available online: https:\/\/openai.com\/api\/pricing\/."},{"key":"ref_60","doi-asserted-by":"crossref","unstructured":"Roumeliotis, K.I., and Tselikas, N.D. (2023). ChatGPT and Open-AI Models: A Preliminary Review. Future Internet, 15.","DOI":"10.3390\/fi15060192"},{"key":"ref_61","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1016\/j.sbspro.2014.07.161","article-title":"The Impact of Information Technology on the Development of Supply Chain Competitive Advantage","volume":"147","author":"Marinagi","year":"2014","journal-title":"Procedia Soc. Behav. Sci."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Gupta, D., Bhargava, A., Agarwal, D., Alsharif, M.H., Uthansakul, P., Uthansakul, M., and Aly, A.A. (2024). Deep Learning-Based Truthful and Deceptive Hotel Reviews. Sustainability, 16.","DOI":"10.3390\/su16114514"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/12\/792\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T16:50:55Z","timestamp":1760115055000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/15\/12\/792"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":62,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["info15120792"],"URL":"https:\/\/doi.org\/10.3390\/info15120792","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]}}}